Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    characters and symbols used in programming or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    special characters and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     desmotivaciones
    -0.73
    ésultats
    -0.71
     fashiola
    -0.65
    -0.65
    𝆺
    -0.64
    <unused41>
    -0.64
    <unused28>
    -0.64
    <unused42>
    -0.63
    <unused17>
    -0.63
    [@BOS@]
    -0.63
    POSITIVE LOGITS
     بيها
    0.34
     Winaray
    0.31
     fanáticos
    0.31
    richTextPanel
    0.31
     Италијани
    0.30
    évaluateur
    0.27
     Numerade
    0.26
     فريبيس
    0.26
    dawnictwo
    0.26
     humaines
    0.26
    Act Density 0.018%

    No Known Activations